Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2766 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0000

Data Index: 908100 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0596. Min Act: -0.0000

Data Index: 73465 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0618. Min Act: -0.0000

Data Index: 157073 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0594. Min Act: -0.0000

Data Index: 65196 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1349862 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0580. Min Act: -0.0000

Data Index: 653506 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1485242 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1320227 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1147633 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1547000 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1021880 (The Pile)

Max Activating Token Index: 2

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0538. Min Act: -0.0000

Data Index: 386908 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1313563 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0531. Min Act: -0.0000

Data Index: 384621 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1868345 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0507. Min Act: -0.0000

Data Index: 15569 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1958639 (The Pile)

Max Activating Token Index: 2

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0520. Min Act: -0.0000

Data Index: 892143 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0516. Min Act: -0.0000

Data Index: 814155 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1081374 (The Pile)

Max Activating Token Index: 6